A method for assessing suicide risk for a human subject including receiving recorded voice data of the subject; and classifying the subject as suicidal or non-suicidal based upon a computerized analysis of one or more nonverbal characteristics of the speech data, especially features associated with a breathy phonation type. The analysis of the nonverbal characteristics of the voice data can include an analysis of acoustic characteristics of speech, and/or an analysis of prosodic and voice quality-related features of the voice data. Related apparatus, systems, techniques and articles are also described.
Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A computer-implemented method for assessing suicide risk in a human subject, the method comprising the steps of: receiving voice data of the subject; and classifying the subject as suicidal or non-suicidal based upon a computerized analysis of one or more nonverbal characteristics of the voice data performed on a support vector machine (SVM) that utilizing hidden Markov models (HMMs), the nonverbal characteristics of the voice data including prosodic and voice quality-related features of the voice data selected from one or more of an acoustic measure of energy in dB (en, en slope ), an acoustic measure of fundamental frequency (f 0 ), an acoustic measure of peak slope (peak), and an acoustic measure of spectral stationarity (ss), the prosodic and voice quality features including an acoustic measure of Liljencrants-Fant (LF) model parameters from time domain estimation methods, including three time-based parameters (R a , R k and R g ) an amplitude parameter (EE), an Open Quotient (OQ), and a parameter characterizing the basic shape of the LF model (R d ) and the classifying including classifying the subject as being suicidal based upon the voice data exhibiting the characteristics of a breathy phonation type.
A computer system assesses suicide risk by analyzing voice data. The system receives a recording of a person's voice and then uses a Support Vector Machine (SVM) combined with Hidden Markov Models (HMMs) to classify the person as either suicidal or non-suicidal. The classification is based on nonverbal characteristics of the voice, specifically prosodic and voice quality features. These features include energy levels (dB), fundamental frequency, peak slope, spectral stationarity, and parameters from the Liljencrants-Fant (LF) model (Ra, Rk, Rg, EE, Open Quotient (OQ), and Rd). The system identifies a "breathy" voice as indicative of suicidal risk.
2. The method of claim 1 , wherein the characteristics of a breathy phonation type are determined based upon one or more acoustic features selected from the group consisting of: Open Quotient (OQ), Normalized Amplitude Quotient (NAQ) and peak slope (peak).
The suicide risk assessment system from the previous description identifies a "breathy" voice, a characteristic associated with suicidal risk, by analyzing specific acoustic features. These features include Open Quotient (OQ), Normalized Amplitude Quotient (NAQ), and peak slope. These values, derived from the voice recording, are used to determine the presence and degree of breathiness, allowing the system to classify the subject as potentially suicidal.
3. The method of claim 2 , wherein the characteristics of a breathy phonation type are determined based upon one or more acoustic features selected from relatively larger R k values and relatively smaller R g values.
Building on the previous description, the system determines if a voice has the breathy characteristic, associated with suicidal risk, by looking at the Liljencrants-Fant (LF) model parameters Rk and Rg. Relatively larger Rk values, combined with relatively smaller Rg values, indicate a breathy voice quality. These specific parameter values are derived from time domain estimation methods performed on the voice data and used by the system to classify the subject as potentially suicidal.
4. A system for assessing suicide risk for a human subject, the system comprising at least one processor, and a non-transitory computer-readable medium containing instructions stored thereon which when executed by the at least one processor, perform a method of assessing suicide risk for the human subject, the method comprising: receiving voice data of the subject; and classifying the subject as suicidal or non-suicidal based upon a computerized analysis of one or more nonverbal characteristics of the voice data performed on a support vector machine (SVM) utilizing hidden Markov models (HMMs), the nonverbal characteristics of the voice data including prosodic and voice quality-related features of the voice data selected from one or more of an acoustic measure of energy in dB (en, en slope ), an acoustic measure of fundamental frequency (f 0 ), an acoustic measure of peak slope (peak), and an acoustic measure of spectral stationarity (ss), the prosodic and voice quality features including an acoustic measure of Liljencrants-Fant (LF) model parameters from time domain estimation methods, including three time-based parameters (R a , R k , R g ) an amplitude parameter (EE), an Open Quotient (OQ), and a parameter characterizing the basic shape of the LF model (R d ) and the classifying including classifying the subject as being suicidal based upon the voice data exhibiting the characteristics of a breathy phonation type.
A suicide risk assessment system includes a processor and memory. The system receives voice data and analyzes nonverbal characteristics to classify the subject as suicidal or non-suicidal. A Support Vector Machine (SVM) with Hidden Markov Models (HMMs) analyzes prosodic and voice quality features, including energy (dB), fundamental frequency, peak slope, spectral stationarity, and Liljencrants-Fant (LF) model parameters (Ra, Rk, Rg, EE, Open Quotient (OQ), and Rd). The system identifies a "breathy" phonation type as indicative of suicidal risk.
5. The system of claim 4 , wherein the characteristics of a breathy phonation type are determined based upon one or more acoustic features selected from the group consisting of: Open Quotient (OQ), Normalized Amplitude Quotient (NAQ) and peak slope (peak) features.
The suicide risk assessment system from the previous description identifies a "breathy" voice, a characteristic associated with suicidal risk, by analyzing specific acoustic features. These features include Open Quotient (OQ), Normalized Amplitude Quotient (NAQ), and peak slope. These values, derived from the voice recording, are used to determine the presence and degree of breathiness, allowing the system to classify the subject as potentially suicidal.
6. The system of claim 5 , wherein the characteristics of a breathy phonation type are determined based upon one or more acoustic features selected from relatively larger R k values, and relatively smaller R g values.
Building on the previous system description, the system determines if a voice has the breathy characteristic, associated with suicidal risk, by looking at the Liljencrants-Fant (LF) model parameters Rk and Rg. Relatively larger Rk values, combined with relatively smaller Rg values, indicate a breathy voice quality. These specific parameter values are derived from time domain estimation methods performed on the voice data and used by the system to classify the subject as potentially suicidal.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
May 23, 2014
June 27, 2017
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.